© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66703
    Prev
    Next
    INDEX
    Explanations

    local places and businesses

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting press‐release style announcements of new store or location openings (e.g. inaugurations, grand-opening notices).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    madeus
    -1.08
    estimable
    -1.08
     ملابس
    -0.99
     главных
    -0.98
    ergies
    -0.97
    foreign
    -0.94
     breite
    -0.91
    global
    -0.91
    omsday
    -0.91
     latter
    -0.91
    POSITIVE LOGITS
     local
    1.57
     your
    1.45
     ваша
    1.25
     nearby
    1.20
    當地
    1.20
     paik
    1.11
     мест
    1.05
     адап
    1.05
     Local
    1.05
    Local
    1.05
    Activations Density 0.086%

    No Known Activations